AI and LLM Application Building — Forward Deployed Engineer (FDE) Roa…
Building AI-powered features and agent workflows for real enterprise use cases
Steps in AI and LLM Application Building
- LLM Application Fundamentals — advanced · The basic architecture of an LLM-powered application: prompts, context, completions and tool calls
- Prompt Engineering for Business Use Cases — advanced · Writing prompts that reliably produce useful output for a specific client workflow, not just a demo
- Retrieval-Augmented Generation (RAG) — advanced · Grounding an LLM's answers in a client's actual documents and data instead of its training data alone
- Building Agent Workflows — advanced · Chaining tool calls, retrieval and reasoning steps into an agent that completes a multi-step task
- Evaluating AI Output Quality — advanced · Measuring whether an AI feature is actually good enough to put in front of a client, and how to keep it that way
- Guardrails and Safety for Client-Facing AI — advanced · Preventing an AI feature from producing harmful, incorrect or off-brand output in front of a client's users
Part of
- Forward Deployed Engineer (FDE) roadmap — the full learning path